English
Related papers

Related papers: On the Overlooked Structure of Stochastic Gradient…

200 papers

Neural network compression techniques have become increasingly popular as they can drastically reduce the storage and computation requirements for very large networks. Recent empirical studies have illustrated that even simple pruning…

Machine Learning · Statistics 2021-06-08 Melih Barsbey , Milad Sefidgaran , Murat A. Erdogdu , Gaël Richard , Umut Şimşekli

In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic)…

Dynamical Systems · Mathematics 2025-07-08 Dennis Chemnitz , Maximilian Engel , Christian Kuehn , Sara-Viola Kuntz

Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong assumptions typically are not satisfied in real-world machine…

Machine Learning · Computer Science 2026-05-26 Xinwen Zhang , Yihan Zhang , Heng Liang , Hongchang Gao

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Optimization and Control · Mathematics 2020-10-26 Jingzhao Zhang , Sai Praneeth Karimireddy , Andreas Veit , Seungyeon Kim , Sashank J Reddi , Sanjiv Kumar , Suvrit Sra

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

This paper studies the distributed optimization problem under the influence of heavy-tailed gradient noises. Here, a heavy-tailed noise means that the noise does not necessarily satisfy the bounded variance assumption. Instead, it satisfies…

Optimization and Control · Mathematics 2025-05-12 Chao Sun , Huiming Zhang , Bo Chen , Li Yu

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving…

Machine Learning · Computer Science 2024-05-30 Feng Chen , Daniel Kunin , Atsushi Yamamura , Surya Ganguli

We scrutinize the structural and operational aspects of deep learning models, particularly focusing on the nuances of learnable parameters (weight) statistics, distribution, node interaction, and visualization. By establishing correlations…

Machine Learning · Computer Science 2024-08-22 Ziwei Zheng , Huizhi Liang , Vaclav Snasel , Vito Latora , Panos Pardalos , Giuseppe Nicosia , Varun Ojha

Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat all parameters as vectors and ignore the matrix structure of modern architectures. We show…

Machine Learning · Computer Science 2026-05-13 Alexander Yukhimchuk , Mladen Kolar , Martin Takáč , Sayantan Choudhury

Establishing a theoretical analysis that explains why deep learning can outperform shallow learning such as kernel methods is one of the biggest issues in the deep learning literature. Towards answering this question, we evaluate excess…

Machine Learning · Statistics 2020-12-08 Taiji Suzuki , Shunta Akiyama

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to…

Machine Learning · Computer Science 2018-07-04 Griffin Lacey , Graham W. Taylor , Shawki Areibi

There are several applications of stochastic optimization where one can benefit from a robust estimate of the gradient. For example, domains such as distributed learning with corrupted nodes, the presence of large outliers in the training…

Machine Learning · Statistics 2025-10-30 Fabian Schaipp , Guillaume Garrigos , Umut Simsekli , Robert Gower

Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the stochastic gradients is heavy-tailed for the later ones.…

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-order optimization algorithms are known to efficiently locate favorable minima in deep neural…

Machine Learning · Computer Science 2023-06-22 Charles Guille-Escuret , Hiroki Naganuma , Kilian Fatras , Ioannis Mitliagkas

How deep neural networks (DNNs) learn from noisy labels has been studied extensively in image classification but much less in image segmentation. So far, our understanding of the learning behavior of DNNs trained by noisy segmentation…

Computer Vision and Pattern Recognition · Computer Science 2022-03-08 Yaoru Luo , Guole Liu , Yuanhao Guo , Ge Yang

\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the…

Machine Learning · Computer Science 2021-06-22 Miao Zhang , Steven Su , Shirui Pan , Xiaojun Chang , Ehsan Abbasnejad , Reza Haffari

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels. In this paper, we find that the test accuracy…

Machine Learning · Computer Science 2019-05-14 Pengfei Chen , Benben Liao , Guangyong Chen , Shengyu Zhang

The stochastic gradient noise (SGN) is a significant factor in the success of stochastic gradient descent (SGD). Following the central limit theorem, SGN was initially modeled as Gaussian, and lately, it has been suggested that stochastic…

Machine Learning · Computer Science 2023-03-07 Barak Battash , Ofir Lindenbaum